Visual inspection method for welding quality of lithium battery pole

By constructing a visual detection model, using the STDCNet network and the pyramid pooling module to extract features, and combining data expansion and loss function adjustment, the problems of low accuracy and insufficient generalization capabilities in the welding quality detection of lithium battery pole are solved, and efficient and accurate detection results are achieved.

CN119672023AActive Publication Date: 2025-03-21JIANGSU MINGYIXIN INTELLIGENT EQUIPMENT CO LTD
3 Cites 0 Cited by

Patent Information

Application Number
CN202510187112.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-20
Publication Date
2025-03-21
Estimated Expiration
2045-02-20

AI Technical Summary

Technical Problem

The prior art has problems in the quality inspection of electrode column welding of lithium batteries with low detection accuracy, insufficient generalization adaptability, slow detection speed, and large samples required.

Method used

A visual detection method is adopted, including obtaining the electrode column welding images and pixel-level annotated images of lithium battery, building a sample set, and extracting features through the STDCNet network, designing a pyramid pooling module and attention fusion module, combining data expansion and loss function adjustment, and training a visual detection model to achieve high-precision detection.

Benefits of technology

It improves the accuracy and speed of electrode column welding quality detection of lithium battery, enhances the generalization adaptability of detection, reduces the dependence on sample number, and achieves more efficient and accurate defect identification.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a visual detection method for the welding quality of a lithium battery pole, and the method comprises the steps: S1, obtaining a lithium battery pole welding image and a pixel-level marking image corresponding to each welding image, and forming a sample set; step S2, carrying out preprocessing on the training sample set train; s3, building a visual detection model; s4, training the visual detection model, storing a training weight file of the visual detection model, and generating the visual detection model; s5, inputting a to-be-tested lithium battery pole welding image into the trained visual detection model to obtain a segmentation result image, and processing the segmentation result image to obtain a semantic segmentation region result image; and S6, performing post-processing on the semantic segmentation region result map, processing and segmenting internal mixing and undersize pixel filtering, and obtaining a final semantic segmentation type region result map. According to the method, the defects of low detection precision, insufficient generalization adaptive capacity, low detection speed and multiple required samples in the prior art are overcome.
Need to check novelty before this filing date? Find Prior Art